3 articles tagged with #kalman-filter. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers propose Online Causal Kalman Filtering for Policy Optimization (KPO) to address high-variance instability in reinforcement learning for large language models. The method uses Kalman filtering to smooth token-level importance sampling ratios, preventing training collapse and achieving superior results on math reasoning tasks.
Researchers demonstrate that High-Resolution Range Profile (HRRP) classifiers achieve significantly better accuracy when incorporating aspect-angle information, showing 7% average improvement and up to 10% gains. The study proves that estimated angles via Kalman filtering can preserve most benefits, making the approach viable for real-world radar and signal processing applications.
Researchers developed a new method for real-time sea state estimation that jointly estimates both sea conditions and vessel parameters without requiring prior knowledge of wave-vessel transfer functions. The approach uses a mass-spring-damper model with advanced filtering techniques to achieve performance matching traditional methods that assume complete transfer function knowledge.
